wikitextparser 0.55.12__tar.gz → 0.56.1__tar.gz

{wikitextparser-0.55.12 → wikitextparser-0.56.1}/.github/workflows/tests.yml

@@ -13,7 +13,7 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest, windows-latest, macos-latest]
-        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
     env:
       OS: ${{ matrix.os }}
       PYTHON: ${{ matrix.python-version }}

{wikitextparser-0.55.12 → wikitextparser-0.56.1}/CHANGELOG.rst

@@ -1,3 +1,19 @@
+v0.56.1
+-------
+* Fixed a bug in ``get_sections`` when ``top_levels_only`` was ``True``.
+
+v0.56.0
+-------
+* Drop Python 3.7 support.
+
+v0.55.14
+--------
+* Fixed a bug in detecting the text of an external link. (#137)
+
+v0.55.13
+--------
+*  Fixed a bug in ``Section.level`` resulting in malformed section titles when multiple levels are added (#135)
+
 v0.55.12
 --------
 * Performance improvements in extracting bold and italic nodes. (#133)

{wikitextparser-0.55.12 → wikitextparser-0.56.1}/PKG-INFO

@@ -1,10 +1,10 @@
 Metadata-Version: 2.1
 Name: wikitextparser
-Version: 0.55.12
+Version: 0.56.1
 Summary: A simple parsing tool for MediaWiki's wikitext markup.
 Keywords: MediaWiki,wikitext,parser
 Author-email: 5j9 <5j9@users.noreply.github.com>
-Requires-Python: >= 3.7
+Requires-Python: >= 3.8
 Description-Content-Type: text/x-rst
 Classifier: Programming Language :: Python
 Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
@@ -38,7 +38,7 @@ The purpose is to allow users easily extract and/or manipulate templates, templa
 Installation
 ============
 
-- Python 3.7+ is required
+- Python 3.8+ is required
 - ``pip install wikitextparser``
 
 Usage

{wikitextparser-0.55.12 → wikitextparser-0.56.1}/README.rst

@@ -19,7 +19,7 @@ The purpose is to allow users easily extract and/or manipulate templates, templa
 Installation
 ============
 
-- Python 3.7+ is required
+- Python 3.8+ is required
 - ``pip install wikitextparser``
 
 Usage

{wikitextparser-0.55.12 → wikitextparser-0.56.1}/pyproject.toml

@@ -19,7 +19,7 @@ classifiers = [
     "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
     "Topic :: Text Processing",
 ]
-requires-python = ">= 3.7"
+requires-python = ">= 3.8"
 dependencies = [
     "regex >= 2022.9.11",
     "wcwidth",

{wikitextparser-0.55.12 → wikitextparser-0.56.1}/wikitextparser/__init__.py

@@ -1,5 +1,5 @@
 # Scheme: [N!]N(.N)*[{a|b|rc}N][.postN][.devN]
-__version__ = '0.55.12'
+__version__ = '0.56.1'
 
 from . import _wikitext
 from ._argument import Argument  # noqa: F401

{wikitextparser-0.55.12 → wikitextparser-0.56.1}/wikitextparser/_parser_function.py

@@ -60,10 +60,7 @@ class SubWikiTextWithArgs(SubWikiText):
             else:
                 arg_span = old_span
             arg = Argument(lststr, type_to_spans, arg_span, type_, self)
-            arg._shadow_cache = (
-                lststr[0][s:e],
-                shadow[arg_self_start:arg_self_end],
-            )
+            arg._span_data[3] = shadow[arg_self_start:arg_self_end]
             arguments_append(arg)
         return arguments
 

{wikitextparser-0.55.12 → wikitextparser-0.56.1}/wikitextparser/_section.py

@@ -42,9 +42,9 @@ class Section(SubWikiText):
         if level_diff == 0:
             return
         if level_diff < 0:
-            new_equals = '=' * abs(level_diff)
+            new_equals = '=' * -level_diff
             self.insert(0, new_equals)
-            self.insert(m.end(2) + 1, new_equals)
+            self.insert(m.end(2) - level_diff, new_equals)
             return
         del self[:level_diff]
         del self[m.end(2) : m.end(2) + level_diff]

{wikitextparser-0.55.12 → wikitextparser-0.56.1}/wikitextparser/_wikitext.py

@@ -40,7 +40,6 @@ from ._spans import (
     END_TAG_PATTERN,
     EXTERNAL_LINK_URL_TAIL,
     INVALID_URL_CHARS,
-    PARSABLE_TAG_EXTENSION_NAME,
     START_TAG_PATTERN,
     parse_to_spans,
     rc,
@@ -52,10 +51,6 @@ NAME_CAPTURING_HTML_START_TAG_FINDITER = rc(
     )
 ).finditer
 
-PARSABLE_TAG_EXTENSIONS_MATCH = rc(
-    rb'<' + PARSABLE_TAG_EXTENSION_NAME + rb'\b', IGNORECASE
-).match
-
 # External links
 BRACKET_EXTERNAL_LINK_SCHEMES = regex_pattern(
     _bare_external_link_schemes | {'//'}
@@ -74,7 +69,7 @@ INVALID_EXT_CHARS_SUB = rc(  # the [:-4] slice allows \[ and \]
 
 # Sections
 SECTION_HEADING = rb'^(?<equals>={1,6})[^\n]+?(?P=equals)[ \t]*+$'
-SUBSECTION_HEADING = rb'^(?P=equals)=[^\n]+?(?P=equals)=[ \t]*+$'
+SUB_SECTION = rb'(?:^(?P=equals)=[^\n]+?(?P=equals)=[ \t]*+$.*?)*'
 LEAD_SECTION = rb'(?<section>(?<equals>).*?)'
 SECTIONS_FULLMATCH = rc(
     LEAD_SECTION
@@ -89,9 +84,8 @@ SECTIONS_TOP_LEVELS_ONLY = rc(
     + rb'(?<section>'
     + SECTION_HEADING
     + rb'.*?'
-    + SUBSECTION_HEADING
-    + rb'.*?'
-    rb')*',
+    + SUB_SECTION
+    + rb')*',
     DOTALL | MULTILINE | VERBOSE,
 ).fullmatch
 
@@ -113,11 +107,7 @@ TABLE_FINDITER = rc(
     DOTALL | MULTILINE | VERBOSE,
 ).finditer
 
-substitute_apostrophes = rc(  # bold-italic, bold, or italic tokens
-    rb"('\0*+){2,}+(?=[^']|$)",
-    MULTILINE | VERBOSE,
-).sub
-find_lines = rc(rb'(.*?)$').finditer
+substitute_apostrophes = rc(rb"('\0*+){2,}+(?=[^']|$)", MULTILINE).sub
 
 BOLD_FINDITER = rc(
     rb"""
@@ -213,7 +203,7 @@ class WikiText:
     # The following class attribute acts as a default value.
     _type = 'WikiText'
 
-    __slots__ = '_type_to_spans', '_lststr', '_span_data', '_shadow_cache'
+    __slots__ = '_type_to_spans', '_lststr', '_span_data'
 
     def __init__(
         self,
@@ -241,7 +231,6 @@ class WikiText:
         if _type not in SPAN_PARSER_TYPES:
             type_to_spans = self._type_to_spans = parse_to_spans(byte_array)
             type_to_spans[_type] = [span]
-            self._shadow_cache = string, byte_array
         else:
             # In SPAN_PARSER_TYPES, we can't pass the original byte_array to
             # parser to generate the shadow because it will replace the whole
@@ -259,7 +248,6 @@ class WikiText:
                 byte_array[0] = 3
                 byte_array[-1] = 32
             type_to_spans = parse_to_spans(byte_array)
-            self._shadow_cache = string, byte_array
             type_to_spans[_type].insert(0, span)
             self._type_to_spans = type_to_spans
             if type(self) is Parameter:
@@ -443,10 +431,7 @@ class WikiText:
     @property
     def span(self) -> tuple:
         """Return the span of self relative to the start of the root node."""
-        # In Python 3.7 and earlier, generalized iterable unpacking in yield
-        # and return statements requires enclosing parentheses:
-        # https://docs.python.org/3.8/whatsnew/3.8.html#other-language-changes
-        return (*self._span_data[:2],)  # noqa
+        return (*self._span_data[:2],)
 
     @property
     def string(self) -> str:
@@ -1072,12 +1057,11 @@ class WikiText:
                 s = starts[1]
                 append_bold_start(s)
                 return b'_' * (s - starts[0]) + m.string[s : m.end()]
-            if n > 5:  # more than 5 apostrophes -> hide the prior ones
-                odd_bold_italics ^= True
-                odd_italics ^= True
-                s = starts[-5]
-                return b'_' * (s - starts[0]) + m.string[s : m.end()]
-            raise  # execution should never reach here
+            # more than 5 apostrophes -> hide the prior ones
+            odd_bold_italics ^= True
+            odd_italics ^= True
+            s = starts[-5]
+            return b'_' * (s - starts[0]) + m.string[s : m.end()]
 
         return bytearray(b'\n').join(
             [
@@ -1206,7 +1190,7 @@ class WikiText:
         )
 
     @property
-    def _ext_link_shadow(self):
+    def _ext_link_shadow(self) -> bytearray:
         """Replace the invalid chars of SPAN_PARSER_TYPES with b'_'.
 
         For comments, all characters are replaced, but for ('Template',
@@ -1216,12 +1200,14 @@ class WikiText:
         byte_array = bytearray(self._lststr[0][ss:se], 'ascii', 'replace')
         subspans = self._subspans
         for s, e, _, _ in subspans('Comment'):
-            byte_array[s:e] = (e - s) * b'_'
+            byte_array[s - ss : e - ss] = (e - s) * b'_'
         for s, e, _, _ in subspans('WikiLink'):
-            byte_array[s:e] = (e - s) * b' '
+            byte_array[s - ss : e - ss] = (e - s) * b' '
         for type_ in 'Template', 'ParserFunction', 'Parameter':
             for s, e, _, _ in subspans(type_):
-                byte_array[s:e] = INVALID_EXT_CHARS_SUB(b' ', byte_array[s:e])
+                byte_array[s - ss : e - ss] = INVALID_EXT_CHARS_SUB(
+                    b' ', byte_array[s:e]
+                )
         return byte_array
 
     @property